Image classification tools in 

Image Analysis for Supervised Classification.

http://www.forestry-gis.info/2010/11/supervised-classification-with-arcgis.html

What You Will Need and Other Assumptions

• A satellite image that has been properly prepared for input to an image classification (e.g.,atmospheric correction, terrain correction, etc.)
• Aerial photographs and other ancillary data for the same area, as well as good local knowledge of the terrain, vegetation and soils for the
area
• The Supervised Classification tools in Image Analysis are very limited as compared to those available in ERDAS Imagine

Overview of Steps
1. Load your satellite image to be classified into ArcMap’s Data Frame.
2. Create and load a polygon Shapefile for collecting your training signatures.
3. Format the Shapefile for signature collection and digitize training sites based on your classification scheme.
4. Specify the required parameters for the Supervised Classification tool and run your classification.
5. Inspect the results, modify existing signatures and collect new ones, and re-run your classification, if necessary.

Step-by-Step Example
1. Start ArcMap from your Desktop, or on the Windows Taskbar click Start | Programs | ArcGIS | ArcMap. Ensure the Image Analysis and
Editor extensions are visible. If not, from ArcMap’s main menu select: 1) Tools | Extensions and enable Image Analysis; 2) View |
Customize and enable Editor; and 3) View | Toolbars and enable Image Analysis and Editor.
2. Use the Add Data button on the main toolbar of ArcMap to add your satellite image to the Data Frame.
3. Click the ArcCatalog button in ArcMap (or start ArcCatalog from the WindowsTaskbar) and navigate to your project directory.
4. In ArcCatalog, click File | New | Shapefile. In the Create New Shapefiledialog, name the new Shapefile in the Name field and change
the Feature Typeto Polygon.
5. Now click the Edit button beneath the Spatial Reference window in theCreate New Shapefile dialog. Click the Import button in
the Spatial Reference Properties dialog, navigate to the directory containing the satellite image you wish to classify, select it and click Add.
Click Apply and OK in the SpatialReference Properties dialog. You have just defined the Spatial Reference for your new Shapefile. Close
ArcCatalog.
6. Use the Add Data button on the main toolbar of ArcMap to add your new Shapefile to the Data Frame.
7. Right-click on your Shapefile and select Open Attribute Table from the pop-up menu. Click the Options button in the attribute table and
select Add Field.
8. In the Add Field dialog, name the new field ClassName (or something similar) and change the Type to Text. Click OK to add the new field
to the table. Leave the attribute table open.
9. From the Editor toolbar, select Editor | Start Editing.
10. Select the Sketch Tool button from the Editor toolbar and digitize your firsttraining site, and ensure the Target is set to your new Shapefile
and the Task is set to Create New Feature (in the Editor toolbar). Note: use Single Left-clicks to add vertices to your polygons and a Double
Left-click to close them.
11. After digitizing your first training site polygon, click in the ClassName field and type the name of your new training site polygon, based
on your classification scheme.
12. Continue digitizing training site polygons and updating the ClassName field of the associated attribute table until you are satisfied that
you’ve collected enoughtraining sites for a complete and representative sample.
13. From the Editor toolbar, select Editor | Stop Editing and close the attribute table when finished collecting training sites. Click Yes when
ArcMap asks if you want to save your edits. Alternatively, you can click Save Edits from the Editorpulldown menu before selecting Stop
Editing. You are now ready to run a first iteration of your classification.
14. From the Image Analysis extension, select Image Analysis | Classification | Supervised. Specify the Input Image (your satellite image
to be classified), theSignature Features (your Shapefile of training sites), and the Class Name Field(ClassName from your training site
Shapefile). Select All Features for the Perform Classification Using option, select a Classification Rule (we recommend Maximum Likelihood,
especially when running a Supervised Classification), and specify a location and filename for the Output Image (your new Supervised
Classification). Click OK.
15. Inspect your results. Collect new signatures, modify existing ones, or delete bad signatures if necessary and rerun your classification until
you achieve acceptable results.